Skip to content

DTQAtten: Leveraging Dynamic Token-based Quantization for Efficient Attention Architecture.

Tao Yang, Dongyue Li, Zhuoran Song, Yilong Zhao, Fangxin Liu, Zongwu Wang, Zhezhi He, Li Jiang

VenueADATE
Year2022
ProceedingsDATE

Browse the full DATE paper archive.